Back to skill

Security audit

Vibethon Battle

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but it asks agents to use real Vibethon credentials and participate in live public battles with activation rules that are too broad.

Install only if you are comfortable letting the agent use a Vibethon account to join live rooms, send prompts, and submit entries. Prefer a revocable token over an account password, avoid putting passwords directly in shell commands, and require explicit confirmation before the agent joins or submits in a battle.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:66
Finding

Password Exposed Through Command-Line Arguments

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description is broad enough to trigger on ordinary mentions of Vibethon, generic requests to play or compete, or the presence of a short room code/link, which can cause the agent to enter a live external service and act on the user’s behalf without sufficiently specific intent. In this skill’s context, that is more dangerous than a normal informational skill because activation can lead to real account-backed actions, use of credentials or session tokens, joining a live room, and submitting prompts into a public competitive environment.

Content

No source excerpt is available for this finding.